Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation

Julian Mack, Rossella Arcucci*, Miguel Molina-Solana, Yi-Ke GUO

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

We propose a new ‘Bi-Reduced Space’ approach to solving 3D Variational Data Assimilation using Convolutional Autoencoders. We prove that our approach has the same solution as previous methods but has significantly lower computational complexity; in other words, we reduce the computational cost without affecting the data assimilation accuracy. We tested our proposal with data from a real-world application: a pollution model of a site in Elephant and Castle (London, UK) and found that we could (1) reduce the size of the background covariance matrix representation by O(103), and (2) increase our data assimilation accuracy with respect to existing reduced space methods.

Original languageEnglish
Article number113291
JournalComputer Methods in Applied Mechanics and Engineering
Volume372
DOIs
Publication statusPublished - 1 Dec 2020

Scopus Subject Areas

  • Computational Mechanics
  • Mechanics of Materials
  • Mechanical Engineering
  • Physics and Astronomy(all)
  • Computer Science Applications

User-Defined Keywords

  • Attention networks
  • Convolutional Autoencoders
  • Variational Data Assimilation

Fingerprint

Dive into the research topics of 'Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation'. Together they form a unique fingerprint.

Cite this